Re: [PATCH v3 7/8] s390/vfio_ccw: implement a channel program mutex

[Matthew Rosato <mjrosato@linux.ibm.com>]

On 7/23/26 1:47 PM, Eric Farman wrote:
> The channel_program struct is manipulated without a serialization
> mechanism to ensure consistent behavior. Take a broad stroke of
> putting the entire structure behind a mutex, and ensure everything
> that needs private->cp holds this mutex.
> 
> There are a couple where the cio layer's subchannel->lock performs
> this role in this code, which isn't correct (it should only be used
> when touching the actual subchannel, like cio_enable_subchannel()),
> so adjust the locations where that spinlock is acquired/released
> to correctly coexist with this new mutex.
> 
> Fixes: 0a19e61e6d4c ("vfio: ccw: introduce channel program interfaces")
> Cc: stable@vger.kernel.org
> Signed-off-by: Eric Farman <farman@linux.ibm.com>
> ---
>  drivers/s390/cio/vfio_ccw_drv.c     | 10 +++++++++-
>  drivers/s390/cio/vfio_ccw_fsm.c     | 22 +++++++++++++++-------
>  drivers/s390/cio/vfio_ccw_ops.c     | 10 +++++++++-
>  drivers/s390/cio/vfio_ccw_private.h |  3 +++
>  4 files changed, 36 insertions(+), 9 deletions(-)
> 
> diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
> index 1a095085bc72..1d8c2ed9da50 100644
> --- a/drivers/s390/cio/vfio_ccw_drv.c
> +++ b/drivers/s390/cio/vfio_ccw_drv.c
> @@ -91,6 +91,8 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
>  
>  	is_final = !(scsw_actl(&irb->scsw) &
>  		     (SCSW_ACTL_DEVACT | SCSW_ACTL_SCHACT));
> +
> +	mutex_lock(&private->cp_mutex);
>  	if (scsw_is_solicited(&irb->scsw)) {
>  		cp_update_scsw(&private->cp, &irb->scsw);
>  		if (is_final && private->state == VFIO_CCW_STATE_CP_PENDING) {
> @@ -98,6 +100,8 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
>  			cp_is_finished = true;
>  		}
>  	}
> +	mutex_unlock(&private->cp_mutex);
> +
>  	mutex_lock(&private->io_mutex);
>  	memcpy(private->io_region->irb_area, irb, sizeof(*irb));
>  	mutex_unlock(&private->io_mutex);
> @@ -259,12 +263,16 @@ static int vfio_ccw_sch_event(struct subchannel *sch, int process)
>  	rc = 0;
>  
>  	if (cio_update_schib(sch)) {
> -		if (private)
> +		if (private) {
> +			spin_unlock_irqrestore(&sch->lock, flags);
>  			vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_NOT_OPER);
> +			goto out;
> +		}
>  	}
>  
>  out_unlock:
>  	spin_unlock_irqrestore(&sch->lock, flags);
> +out:
>  
>  	return rc;
>  }
> diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
> index 4d7988ea47ef..9fbe97bd23f9 100644
> --- a/drivers/s390/cio/vfio_ccw_fsm.c
> +++ b/drivers/s390/cio/vfio_ccw_fsm.c
> @@ -25,17 +25,15 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
>  	unsigned long flags;
>  	int ret;
>  
> -	spin_lock_irqsave(&sch->lock, flags);
> -
>  	orb = cp_get_orb(&private->cp, sch);

Can you extend the documentation for cp_get_orb to indicate that
cp_mutex must be held on entry?

Actually, better yet, can you use lockdep_assert_held()?

Would be a good idea to put these also in other functions that have now
an implicit expectation that the mutex will be held, here's the list I
came up with?

cp_get_orb
cp_init
cp_prefetch
cp_free
fsm_io_helper
cp_iova_pinned	
cp_update_scsw

In some cases (like cp_get_orb) you'd have to do something like:
    struct vfio_ccw_private *private = container_of(cp, struct vfio_ccw_private, cp);
    lockdep_assert_held(&private->cp_mutex);

Then this lets us also use lockdep to make sure the mutex is OK now
and in the future.

> -	if (!orb) {
> -		ret = -EIO;
> -		goto out;
> -	}
> +	if (!orb)
> +		return -EIO;
>  
>  	VFIO_CCW_TRACE_EVENT(5, "stIO");
>  	VFIO_CCW_TRACE_EVENT(5, dev_name(&sch->dev));
>  
> +	spin_lock_irqsave(&sch->lock, flags);
> +
>  	/* Issue "Start Subchannel" */
>  	ccode = ssch(sch->schid, orb);
>  
> @@ -71,7 +69,6 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
>  	default:
>  		ret = ccode;
>  	}
> -out:
>  	spin_unlock_irqrestore(&sch->lock, flags);
>  	return ret;
>  }
> @@ -171,7 +168,9 @@ static void fsm_notoper(struct vfio_ccw_private *private,
>  	private->state = VFIO_CCW_STATE_NOT_OPER;
>  
>  	/* This is usually handled during CLOSE event */
> +	mutex_lock(&private->cp_mutex);
>  	cp_free(&private->cp);
> +	mutex_unlock(&private->cp_mutex);
>  }
>  
>  /*
> @@ -252,6 +251,8 @@ static void fsm_io_request(struct vfio_ccw_private *private,
>  	private->state = VFIO_CCW_STATE_CP_PROCESSING;
>  	memcpy(scsw, io_region->scsw_area, sizeof(*scsw));
>  
> +	mutex_lock(&private->cp_mutex);
> +
>  	if (scsw->cmd.fctl & SCSW_FCTL_START_FUNC) {
>  		orb = (union orb *)io_region->orb_area;
>  
> @@ -300,6 +301,8 @@ static void fsm_io_request(struct vfio_ccw_private *private,
>  			cp_free(&private->cp);
>  			goto err_out;
>  		}
> +
> +		mutex_unlock(&private->cp_mutex);
>  		return;
>  	} else if (scsw->cmd.fctl & SCSW_FCTL_HALT_FUNC) {
>  		VFIO_CCW_MSG_EVENT(2,
> @@ -320,6 +323,7 @@ static void fsm_io_request(struct vfio_ccw_private *private,
>  	}
>  
>  err_out:
> +	mutex_unlock(&private->cp_mutex);
>  	private->state = VFIO_CCW_STATE_IDLE;
>  	trace_vfio_ccw_fsm_io_request(scsw->cmd.fctl, schid,
>  				      io_region->ret_code, errstr);
> @@ -410,7 +414,11 @@ static void fsm_close(struct vfio_ccw_private *private,
>  
>  	private->state = VFIO_CCW_STATE_STANDBY;
>  	spin_unlock_irq(&sch->lock);
> +
> +	mutex_lock(&private->cp_mutex);
>  	cp_free(&private->cp);
> +	mutex_unlock(&private->cp_mutex);
> +
>  	return;
>  
>  err_unlock:
> diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
> index 032a1cdf4df7..04800cfa779b 100644
> --- a/drivers/s390/cio/vfio_ccw_ops.c
> +++ b/drivers/s390/cio/vfio_ccw_ops.c
> @@ -38,8 +38,13 @@ static void vfio_ccw_dma_unmap(struct vfio_device *vdev, u64 iova, u64 length)
>  		container_of(vdev, struct vfio_ccw_private, vdev);
>  
>  	/* Drivers MUST unpin pages in response to an invalidation. */
> -	if (!cp_iova_pinned(&private->cp, iova, length))
> +	mutex_lock(&private->cp_mutex);
> +	if (!cp_iova_pinned(&private->cp, iova, length)) {
> +		mutex_unlock(&private->cp_mutex);
>  		return;
> +	}
> +
> +	mutex_unlock(&private->cp_mutex);
>  
>  	vfio_ccw_mdev_reset(private);
>  }
> @@ -50,6 +55,7 @@ static int vfio_ccw_mdev_init_dev(struct vfio_device *vdev)
>  		container_of(vdev, struct vfio_ccw_private, vdev);
>  
>  	mutex_init(&private->io_mutex);
> +	mutex_init(&private->cp_mutex);
>  	private->state = VFIO_CCW_STATE_STANDBY;
>  	INIT_LIST_HEAD(&private->crw);
>  	INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo);
> @@ -90,6 +96,7 @@ static int vfio_ccw_mdev_init_dev(struct vfio_device *vdev)
>  out_free_cp:
>  	kfree(private->cp.guest_cp);
>  out_free_private:
> +	mutex_destroy(&private->cp_mutex);
>  	mutex_destroy(&private->io_mutex);
>  	return -ENOMEM;
>  }
> @@ -141,6 +148,7 @@ static void vfio_ccw_mdev_release_dev(struct vfio_device *vdev)
>  	kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region);
>  	kmem_cache_free(vfio_ccw_io_region, private->io_region);
>  	kfree(private->cp.guest_cp);
> +	mutex_destroy(&private->cp_mutex);
>  	mutex_destroy(&private->io_mutex);
>  }
>  
> diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
> index 0501d4bbcdbd..ac5aaa78a74b 100644
> --- a/drivers/s390/cio/vfio_ccw_private.h
> +++ b/drivers/s390/cio/vfio_ccw_private.h
> @@ -94,6 +94,7 @@ struct vfio_ccw_parent {
>   * @schib_region: MMIO region for SCHIB information
>   * @crw_region: MMIO region for getting channel report words
>   * @num_regions: number of additional regions
> + * @cp_mutex: protect against concurrent update of CP resources
>   * @cp: channel program for the current I/O operation
>   * @irb: irb info received from interrupt
>   * @scsw: scsw info
> @@ -115,7 +116,9 @@ struct vfio_ccw_private {
>  	struct ccw_crw_region	*crw_region;
>  	int num_regions;
>  
> +	struct mutex		cp_mutex;
>  	struct channel_program	cp;
> +
>  	struct irb		irb;
>  	union scsw		scsw;
>  	struct list_head	crw;